© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15389
    Prev
    Next
    INDEX
    Explanations

    say spirit

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    トー
    -18.50
     Harris
    -17.63
     newObj
    -16.50
    衰退
    -16.50
    bject
    -16.50
     objeto
    -16.38
    -roll
    -16.38
    坍
    -16.25
    /tag
    -15.69
    /object
    -15.50
    POSITIVE LOGITS
     spirit
    32.00
    精神
    31.00
     Spirit
    30.88
    灵魂
    29.75
    心理
    29.38
     soul
    29.25
    的精神
    29.13
     spirits
    28.25
     mental
    27.88
     Soul
    27.63
    Activations Density 0.246%

    No Known Activations